Designing a recommendation function for semantic merging of middle-of-life data streams
F. Abou Eddahab-Burke (TU Delft - System Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
This paper addresses the challenge of handling large and diverse data streams from connected products during middle-of-life use. Current data analytics tools struggle with such data, necessitating the development of a crucial function in next-generation data analytics tools that semantically merges and analyzes these streams collectively. The proposed function, recommendation for semantic merging of middle-of-life, acquires, pre-processes, and merges data from various streams, providing designers with enhanced product information. Tested on simulated data streams of a washing machine enhancement case, the function offers more comprehensive product insights than individual sensor analysis. Implementation of such a function could improve fidelity in reflecting product conditions, reduce sensor analysis time and effort, and deliver an actionable plan for product improvement. Being design-focused, this article addresses the functional validity and the proof of concept of the recommendation function. Full computational analysis is out of this paper’s scope and will be addressed in future research.
help_outline